We use analytics and minimal tracking across our websites to help improve performance and user experience. Our privacy policy.
curl --request POST \
--url https://api.private-ai.com/deid/v3/process/text/reidentify \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"processed_text": [
"<string>"
],
"entities": [
{
"processed_text": "<string>",
"text": "<string>"
}
],
"model": "<string>"
}
'[
"<string>"
]This route is intended to improve integrations with LLMs such as ChatGPT. Entities that are removed prior to sending to the LLM can be re-injected into the response from the LLM to improve user experience.
curl --request POST \
--url https://api.private-ai.com/deid/v3/process/text/reidentify \
--header 'Content-Type: application/json' \
--header 'x-api-key: <api-key>' \
--data '
{
"processed_text": [
"<string>"
],
"entities": [
{
"processed_text": "<string>",
"text": "<string>"
}
],
"model": "<string>"
}
'[
"<string>"
]The text with redaction markers. The markers will be replaced with the entity texts. E.g. Hi [NAME_1], nice to meet you.
A list of all entities found in the text.
Show child attributes
The LLM that provides the completions. E.g. gpt3.5-turbo. While optional, this is used to improve the re-identification process by accounting for the model's unique behaviour surrounding redaction markers
Successful Response